© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 12818
    Prev
    Next
    INDEX
    Explanations

    mentions of election-related terms such as votes, percentages, electoral votes, and candidates

    oai_token-act-pair · gpt-3.5-turbo

    numerical data related to votes and electoral results

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    iHUD
    -0.71
    sym
    -0.70
    tnc
    -0.68
    tty
    -0.64
    emis
    -0.63
    SpaceEngineers
    -0.63
    çīĪ
    -0.63
    MJ
    -0.63
    bly
    -0.61
    ilage
    -0.61
    POSITIVE LOGITS
     cast
    1.20
     counted
    1.14
     tallied
    1.08
     apiece
    0.93
     needed
    0.92
     ballots
    0.88
     votes
    0.86
     casting
    0.84
     collected
    0.84
     amassed
    0.84
    Activations Density 0.095%

    No Known Activations